From 4965fc38c460b274b2a1789e1165a25fb0409d7e Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 23 Oct 2014 16:32:57 +0400 Subject: libceph: nuke ceph_kvfree() Use kvfree() from linux/mm.h instead, which is identical. Also fix the ceph_buffer comment: we will allocate with kmalloc() up to 32k - the value of PAGE_ALLOC_COSTLY_ORDER, but that really is just an implementation detail so don't mention it at all. Signed-off-by: Ilya Dryomov --- net/ceph/buffer.c | 4 ++-- net/ceph/ceph_common.c | 8 -------- net/ceph/messenger.c | 2 +- 3 files changed, 3 insertions(+), 11 deletions(-) (limited to 'net') diff --git a/net/ceph/buffer.c b/net/ceph/buffer.c index 621b5f65407f..add5f921a0ff 100644 --- a/net/ceph/buffer.c +++ b/net/ceph/buffer.c @@ -6,7 +6,7 @@ #include #include -#include /* for ceph_kv{malloc,free} */ +#include /* for ceph_kvmalloc */ struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp) { @@ -35,7 +35,7 @@ void ceph_buffer_release(struct kref *kref) struct ceph_buffer *b = container_of(kref, struct ceph_buffer, kref); dout("buffer_release %p\n", b); - ceph_kvfree(b->vec.iov_base); + kvfree(b->vec.iov_base); kfree(b); } EXPORT_SYMBOL(ceph_buffer_release); diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 58fbfe134f93..d361a274aee7 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -184,14 +184,6 @@ void *ceph_kvmalloc(size_t size, gfp_t flags) return __vmalloc(size, flags | __GFP_HIGHMEM, PAGE_KERNEL); } -void ceph_kvfree(const void *ptr) -{ - if (is_vmalloc_addr(ptr)) - vfree(ptr); - else - kfree(ptr); -} - static int parse_fsid(const char *str, struct ceph_fsid *fsid) { diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 8d1653caffdb..863d07ab2129 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -3288,7 +3288,7 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip) static void ceph_msg_free(struct ceph_msg *m) { dout("%s %p\n", __func__, m); - ceph_kvfree(m->front.iov_base); + kvfree(m->front.iov_base); kmem_cache_free(ceph_msg_cache, m); } -- cgit v1.2.3 From ae385eaf24dc39c1703049112e4265b9f93b7d86 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 4 Nov 2014 16:32:35 +0800 Subject: libceph: store session key in cephx authorizer Session key is required when calculating message signature. Save the session key in authorizer, this avoid lookup ticket handler for each message Signed-off-by: Yan, Zheng --- net/ceph/auth_x.c | 18 +++++++++++------- net/ceph/auth_x.h | 1 + 2 files changed, 12 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 7e38b729696a..77f3885c16bc 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -293,6 +293,11 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac, dout("build_authorizer for %s %p\n", ceph_entity_type_name(th->service), au); + ceph_crypto_key_destroy(&au->session_key); + ret = ceph_crypto_key_clone(&au->session_key, &th->session_key); + if (ret) + return ret; + maxlen = sizeof(*msg_a) + sizeof(msg_b) + ceph_x_encrypt_buflen(ticket_blob_len); dout(" need len %d\n", maxlen); @@ -302,8 +307,10 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac, } if (!au->buf) { au->buf = ceph_buffer_new(maxlen, GFP_NOFS); - if (!au->buf) + if (!au->buf) { + ceph_crypto_key_destroy(&au->session_key); return -ENOMEM; + } } au->service = th->service; au->secret_id = th->secret_id; @@ -329,7 +336,7 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac, get_random_bytes(&au->nonce, sizeof(au->nonce)); msg_b.struct_v = 1; msg_b.nonce = cpu_to_le64(au->nonce); - ret = ceph_x_encrypt(&th->session_key, &msg_b, sizeof(msg_b), + ret = ceph_x_encrypt(&au->session_key, &msg_b, sizeof(msg_b), p, end - p); if (ret < 0) goto out_buf; @@ -588,17 +595,13 @@ static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac, struct ceph_authorizer *a, size_t len) { struct ceph_x_authorizer *au = (void *)a; - struct ceph_x_ticket_handler *th; int ret = 0; struct ceph_x_authorize_reply reply; void *preply = &reply; void *p = au->reply_buf; void *end = p + sizeof(au->reply_buf); - th = get_ticket_handler(ac, au->service); - if (IS_ERR(th)) - return PTR_ERR(th); - ret = ceph_x_decrypt(&th->session_key, &p, end, &preply, sizeof(reply)); + ret = ceph_x_decrypt(&au->session_key, &p, end, &preply, sizeof(reply)); if (ret < 0) return ret; if (ret != sizeof(reply)) @@ -618,6 +621,7 @@ static void ceph_x_destroy_authorizer(struct ceph_auth_client *ac, { struct ceph_x_authorizer *au = (void *)a; + ceph_crypto_key_destroy(&au->session_key); ceph_buffer_put(au->buf); kfree(au); } diff --git a/net/ceph/auth_x.h b/net/ceph/auth_x.h index 65ee72082d99..e8b7c6917d47 100644 --- a/net/ceph/auth_x.h +++ b/net/ceph/auth_x.h @@ -26,6 +26,7 @@ struct ceph_x_ticket_handler { struct ceph_x_authorizer { + struct ceph_crypto_key session_key; struct ceph_buffer *buf; unsigned int service; u64 nonce; -- cgit v1.2.3 From 33d07337962c7bbd2fd5cf7f1106735c9507fbe2 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 4 Nov 2014 16:33:37 +0800 Subject: libceph: message signature support Signed-off-by: Yan, Zheng --- fs/ceph/mds_client.c | 16 +++++++++++ include/linux/ceph/auth.h | 26 +++++++++++++++++ include/linux/ceph/ceph_features.h | 1 + include/linux/ceph/messenger.h | 9 +++++- include/linux/ceph/msgr.h | 8 ++++++ net/ceph/auth_x.c | 58 ++++++++++++++++++++++++++++++++++++++ net/ceph/messenger.c | 32 +++++++++++++++++++-- net/ceph/osd_client.c | 16 +++++++++++ 8 files changed, 162 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index fc74617069a3..9f00853f6d42 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3744,6 +3744,20 @@ static struct ceph_msg *mds_alloc_msg(struct ceph_connection *con, return msg; } +static int sign_message(struct ceph_connection *con, struct ceph_msg *msg) +{ + struct ceph_mds_session *s = con->private; + struct ceph_auth_handshake *auth = &s->s_auth; + return ceph_auth_sign_message(auth, msg); +} + +static int check_message_signature(struct ceph_connection *con, struct ceph_msg *msg) +{ + struct ceph_mds_session *s = con->private; + struct ceph_auth_handshake *auth = &s->s_auth; + return ceph_auth_check_message_signature(auth, msg); +} + static const struct ceph_connection_operations mds_con_ops = { .get = con_get, .put = con_put, @@ -3753,6 +3767,8 @@ static const struct ceph_connection_operations mds_con_ops = { .invalidate_authorizer = invalidate_authorizer, .peer_reset = peer_reset, .alloc_msg = mds_alloc_msg, + .sign_message = sign_message, + .check_message_signature = check_message_signature, }; /* eof */ diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h index 5f3386844134..260d78b587c4 100644 --- a/include/linux/ceph/auth.h +++ b/include/linux/ceph/auth.h @@ -13,6 +13,7 @@ struct ceph_auth_client; struct ceph_authorizer; +struct ceph_msg; struct ceph_auth_handshake { struct ceph_authorizer *authorizer; @@ -20,6 +21,10 @@ struct ceph_auth_handshake { size_t authorizer_buf_len; void *authorizer_reply_buf; size_t authorizer_reply_buf_len; + int (*sign_message)(struct ceph_auth_handshake *auth, + struct ceph_msg *msg); + int (*check_message_signature)(struct ceph_auth_handshake *auth, + struct ceph_msg *msg); }; struct ceph_auth_client_ops { @@ -66,6 +71,11 @@ struct ceph_auth_client_ops { void (*reset)(struct ceph_auth_client *ac); void (*destroy)(struct ceph_auth_client *ac); + + int (*sign_message)(struct ceph_auth_handshake *auth, + struct ceph_msg *msg); + int (*check_message_signature)(struct ceph_auth_handshake *auth, + struct ceph_msg *msg); }; struct ceph_auth_client { @@ -113,4 +123,20 @@ extern int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac, extern void ceph_auth_invalidate_authorizer(struct ceph_auth_client *ac, int peer_type); +static inline int ceph_auth_sign_message(struct ceph_auth_handshake *auth, + struct ceph_msg *msg) +{ + if (auth->sign_message) + return auth->sign_message(auth, msg); + return 0; +} + +static inline +int ceph_auth_check_message_signature(struct ceph_auth_handshake *auth, + struct ceph_msg *msg) +{ + if (auth->check_message_signature) + return auth->check_message_signature(auth, msg); + return 0; +} #endif diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index d12659ce550d..71e05bbf8ceb 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -84,6 +84,7 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_PGPOOL3 | \ CEPH_FEATURE_OSDENC | \ CEPH_FEATURE_CRUSH_TUNABLES | \ + CEPH_FEATURE_MSG_AUTH | \ CEPH_FEATURE_CRUSH_TUNABLES2 | \ CEPH_FEATURE_REPLY_CREATE_INODE | \ CEPH_FEATURE_OSDHASHPSPOOL | \ diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 40ae58e3e9db..d9d396c16503 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -42,6 +42,10 @@ struct ceph_connection_operations { struct ceph_msg * (*alloc_msg) (struct ceph_connection *con, struct ceph_msg_header *hdr, int *skip); + int (*sign_message) (struct ceph_connection *con, struct ceph_msg *msg); + + int (*check_message_signature) (struct ceph_connection *con, + struct ceph_msg *msg); }; /* use format string %s%d */ @@ -142,7 +146,10 @@ struct ceph_msg_data_cursor { */ struct ceph_msg { struct ceph_msg_header hdr; /* header */ - struct ceph_msg_footer footer; /* footer */ + union { + struct ceph_msg_footer footer; /* footer */ + struct ceph_msg_footer_old old_footer; /* old format footer */ + }; struct kvec front; /* unaligned blobs of message */ struct ceph_buffer *middle; diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h index 3d94a73b5f30..cac4b28ac1c0 100644 --- a/include/linux/ceph/msgr.h +++ b/include/linux/ceph/msgr.h @@ -164,13 +164,21 @@ struct ceph_msg_header { /* * follows data payload */ +struct ceph_msg_footer_old { + __le32 front_crc, middle_crc, data_crc; + __u8 flags; +} __attribute__ ((packed)); + struct ceph_msg_footer { __le32 front_crc, middle_crc, data_crc; + // sig holds the 64 bits of the digital signature for the message PLR + __le64 sig; __u8 flags; } __attribute__ ((packed)); #define CEPH_MSG_FOOTER_COMPLETE (1<<0) /* msg wasn't aborted */ #define CEPH_MSG_FOOTER_NOCRC (1<<1) /* no data crc */ +#define CEPH_MSG_FOOTER_SIGNED (1<<2) /* msg was signed */ #endif diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 77f3885c16bc..15845814a0f2 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -8,6 +8,7 @@ #include #include +#include #include "crypto.h" #include "auth_x.h" @@ -567,6 +568,8 @@ static int ceph_x_create_authorizer( auth->authorizer_buf_len = au->buf->vec.iov_len; auth->authorizer_reply_buf = au->reply_buf; auth->authorizer_reply_buf_len = sizeof (au->reply_buf); + auth->sign_message = ac->ops->sign_message; + auth->check_message_signature = ac->ops->check_message_signature; return 0; } @@ -667,6 +670,59 @@ static void ceph_x_invalidate_authorizer(struct ceph_auth_client *ac, memset(&th->validity, 0, sizeof(th->validity)); } +static int calcu_signature(struct ceph_x_authorizer *au, + struct ceph_msg *msg, __le64 *sig) +{ + int ret; + char tmp_enc[40]; + __le32 tmp[5] = { + 16u, msg->hdr.crc, msg->footer.front_crc, + msg->footer.middle_crc, msg->footer.data_crc, + }; + ret = ceph_x_encrypt(&au->session_key, &tmp, sizeof(tmp), + tmp_enc, sizeof(tmp_enc)); + if (ret < 0) + return ret; + *sig = *(__le64*)(tmp_enc + 4); + return 0; +} + +static int ceph_x_sign_message(struct ceph_auth_handshake *auth, + struct ceph_msg *msg) +{ + int ret; + if (!auth->authorizer) + return 0; + ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer, + msg, &msg->footer.sig); + if (ret < 0) + return ret; + msg->footer.flags |= CEPH_MSG_FOOTER_SIGNED; + return 0; +} + +static int ceph_x_check_message_signature(struct ceph_auth_handshake *auth, + struct ceph_msg *msg) +{ + __le64 sig_check; + int ret; + + if (!auth->authorizer) + return 0; + ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer, + msg, &sig_check); + if (ret < 0) + return ret; + if (sig_check == msg->footer.sig) + return 0; + if (msg->footer.flags & CEPH_MSG_FOOTER_SIGNED) + dout("ceph_x_check_message_signature %p has signature %llx " + "expect %llx\n", msg, msg->footer.sig, sig_check); + else + dout("ceph_x_check_message_signature %p sender did not set " + "CEPH_MSG_FOOTER_SIGNED\n", msg); + return -EBADMSG; +} static const struct ceph_auth_client_ops ceph_x_ops = { .name = "x", @@ -681,6 +737,8 @@ static const struct ceph_auth_client_ops ceph_x_ops = { .invalidate_authorizer = ceph_x_invalidate_authorizer, .reset = ceph_x_reset, .destroy = ceph_x_destroy, + .sign_message = ceph_x_sign_message, + .check_message_signature = ceph_x_check_message_signature, }; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 863d07ab2129..33a2f201e460 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1196,8 +1196,18 @@ static void prepare_write_message_footer(struct ceph_connection *con) dout("prepare_write_message_footer %p\n", con); con->out_kvec_is_msg = true; con->out_kvec[v].iov_base = &m->footer; - con->out_kvec[v].iov_len = sizeof(m->footer); - con->out_kvec_bytes += sizeof(m->footer); + if (con->peer_features & CEPH_FEATURE_MSG_AUTH) { + if (con->ops->sign_message) + con->ops->sign_message(con, m); + else + m->footer.sig = 0; + con->out_kvec[v].iov_len = sizeof(m->footer); + con->out_kvec_bytes += sizeof(m->footer); + } else { + m->old_footer.flags = m->footer.flags; + con->out_kvec[v].iov_len = sizeof(m->old_footer); + con->out_kvec_bytes += sizeof(m->old_footer); + } con->out_kvec_left++; con->out_more = m->more_to_follow; con->out_msg_done = true; @@ -2249,6 +2259,7 @@ static int read_partial_message(struct ceph_connection *con) int ret; unsigned int front_len, middle_len, data_len; bool do_datacrc = !con->msgr->nocrc; + bool need_sign = (con->peer_features & CEPH_FEATURE_MSG_AUTH); u64 seq; u32 crc; @@ -2361,12 +2372,21 @@ static int read_partial_message(struct ceph_connection *con) } /* footer */ - size = sizeof (m->footer); + if (need_sign) + size = sizeof(m->footer); + else + size = sizeof(m->old_footer); + end += size; ret = read_partial(con, end, size, &m->footer); if (ret <= 0) return ret; + if (!need_sign) { + m->footer.flags = m->old_footer.flags; + m->footer.sig = 0; + } + dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n", m, front_len, m->footer.front_crc, middle_len, m->footer.middle_crc, data_len, m->footer.data_crc); @@ -2390,6 +2410,12 @@ static int read_partial_message(struct ceph_connection *con) return -EBADMSG; } + if (need_sign && con->ops->check_message_signature && + con->ops->check_message_signature(con, m)) { + pr_err("read_partial_message %p signature check failed\n", m); + return -EBADMSG; + } + return 1; /* done! */ } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 6f164289bde8..1f6c4055adaf 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -2920,6 +2920,20 @@ static int invalidate_authorizer(struct ceph_connection *con) return ceph_monc_validate_auth(&osdc->client->monc); } +static int sign_message(struct ceph_connection *con, struct ceph_msg *msg) +{ + struct ceph_osd *o = con->private; + struct ceph_auth_handshake *auth = &o->o_auth; + return ceph_auth_sign_message(auth, msg); +} + +static int check_message_signature(struct ceph_connection *con, struct ceph_msg *msg) +{ + struct ceph_osd *o = con->private; + struct ceph_auth_handshake *auth = &o->o_auth; + return ceph_auth_check_message_signature(auth, msg); +} + static const struct ceph_connection_operations osd_con_ops = { .get = get_osd_con, .put = put_osd_con, @@ -2928,5 +2942,7 @@ static const struct ceph_connection_operations osd_con_ops = { .verify_authorizer_reply = verify_authorizer_reply, .invalidate_authorizer = invalidate_authorizer, .alloc_msg = alloc_msg, + .sign_message = sign_message, + .check_message_signature = check_message_signature, .fault = osd_reset, }; -- cgit v1.2.3 From a3fc98005c9c6e4649d26bee0935a7048a95c9e6 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 11 Nov 2014 16:30:55 +0800 Subject: libceph: require cephx message signature by default Signed-off-by: Yan, Zheng Reviewed-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 1 + net/ceph/ceph_common.c | 13 +++++++++++++ 2 files changed, 14 insertions(+) (limited to 'net') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index d293f7e38814..8b11a79ca1cb 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -29,6 +29,7 @@ #define CEPH_OPT_NOSHARE (1<<1) /* don't share client with other sbs */ #define CEPH_OPT_MYIP (1<<2) /* specified my ip */ #define CEPH_OPT_NOCRC (1<<3) /* no data crc on writes */ +#define CEPH_OPT_NOMSGAUTH (1<<4) /* not require cephx message signature */ #define CEPH_OPT_DEFAULT (0) diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index d361a274aee7..5d5ab67f516d 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -237,6 +237,8 @@ enum { Opt_noshare, Opt_crc, Opt_nocrc, + Opt_cephx_require_signatures, + Opt_nocephx_require_signatures, }; static match_table_t opt_tokens = { @@ -255,6 +257,8 @@ static match_table_t opt_tokens = { {Opt_noshare, "noshare"}, {Opt_crc, "crc"}, {Opt_nocrc, "nocrc"}, + {Opt_cephx_require_signatures, "cephx_require_signatures"}, + {Opt_nocephx_require_signatures, "nocephx_require_signatures"}, {-1, NULL} }; @@ -453,6 +457,12 @@ ceph_parse_options(char *options, const char *dev_name, case Opt_nocrc: opt->flags |= CEPH_OPT_NOCRC; break; + case Opt_cephx_require_signatures: + opt->flags &= ~CEPH_OPT_NOMSGAUTH; + break; + case Opt_nocephx_require_signatures: + opt->flags |= CEPH_OPT_NOMSGAUTH; + break; default: BUG_ON(token); @@ -496,6 +506,9 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, init_waitqueue_head(&client->auth_wq); client->auth_err = 0; + if (!ceph_test_opt(client, NOMSGAUTH)) + required_features |= CEPH_FEATURE_MSG_AUTH; + client->extra_mon_dispatch = NULL; client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT | supported_features; -- cgit v1.2.3 From d74b50bed037794135cb5a4e7418ad71d9848ce1 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Wed, 12 Nov 2014 14:00:43 +0800 Subject: libceph: add SETXATTR/CMPXATTR osd operations support Signed-off-by: Yan, Zheng Reviewed-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 10 +++++++++ net/ceph/osd_client.c | 47 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) (limited to 'net') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 03aeb27fcc69..bcf9c2180ea5 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -86,6 +86,13 @@ struct ceph_osd_req_op { u32 truncate_seq; struct ceph_osd_data osd_data; } extent; + struct { + __le32 name_len; + __le32 value_len; + __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */ + __u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */ + struct ceph_osd_data osd_data; + } xattr; struct { const char *class_name; const char *method_name; @@ -295,6 +302,9 @@ extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, const char *class, const char *method); +extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which, + u16 opcode, const char *name, const void *value, + size_t size, u8 cmp_op, u8 cmp_mode); extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u64 cookie, u64 version, int flag); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 1f6c4055adaf..2b0555b36e4d 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -292,6 +292,10 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req, ceph_osd_data_release(&op->cls.request_data); ceph_osd_data_release(&op->cls.response_data); break; + case CEPH_OSD_OP_SETXATTR: + case CEPH_OSD_OP_CMPXATTR: + ceph_osd_data_release(&op->xattr.osd_data); + break; default: break; } @@ -545,6 +549,39 @@ void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, } EXPORT_SYMBOL(osd_req_op_cls_init); +int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which, + u16 opcode, const char *name, const void *value, + size_t size, u8 cmp_op, u8 cmp_mode) +{ + struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which, opcode); + struct ceph_pagelist *pagelist; + size_t payload_len; + + BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR); + + pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS); + if (!pagelist) + return -ENOMEM; + + ceph_pagelist_init(pagelist); + + payload_len = strlen(name); + op->xattr.name_len = payload_len; + ceph_pagelist_append(pagelist, name, payload_len); + + op->xattr.value_len = size; + ceph_pagelist_append(pagelist, value, size); + payload_len += size; + + op->xattr.cmp_op = cmp_op; + op->xattr.cmp_mode = cmp_mode; + + ceph_osd_data_pagelist_init(&op->xattr.osd_data, pagelist); + op->payload_len = payload_len; + return 0; +} +EXPORT_SYMBOL(osd_req_op_xattr_init); + void osd_req_op_watch_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u64 cookie, u64 version, int flag) @@ -676,6 +713,16 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req, dst->alloc_hint.expected_write_size = cpu_to_le64(src->alloc_hint.expected_write_size); break; + case CEPH_OSD_OP_SETXATTR: + case CEPH_OSD_OP_CMPXATTR: + dst->xattr.name_len = cpu_to_le32(src->xattr.name_len); + dst->xattr.value_len = cpu_to_le32(src->xattr.value_len); + dst->xattr.cmp_op = src->xattr.cmp_op; + dst->xattr.cmp_mode = src->xattr.cmp_mode; + osd_data = &src->xattr.osd_data; + ceph_osdc_msg_data_add(req->r_request, osd_data); + request_data_len = osd_data->pagelist->length; + break; default: pr_err("unsupported osd opcode %s\n", ceph_osd_op_name(src->op)); -- cgit v1.2.3 From 864e9197f10c77053bbaf12932f5b200bb4ed3c5 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Thu, 13 Nov 2014 10:47:25 +0800 Subject: libceph: add CREATE osd operation support Add CEPH_OSD_OP_CREATE support. Also change libceph to not treat CEPH_OSD_OP_DELETE as an extent op and add an assert to that end. Signed-off-by: Yan, Zheng Reviewed-by: Ilya Dryomov --- net/ceph/osd_client.c | 42 ++++++++++++++++++++++-------------------- 1 file changed, 22 insertions(+), 20 deletions(-) (limited to 'net') diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 2b0555b36e4d..af1b3ee195e9 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -480,8 +480,7 @@ void osd_req_op_extent_init(struct ceph_osd_request *osd_req, size_t payload_len = 0; BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE && - opcode != CEPH_OSD_OP_DELETE && opcode != CEPH_OSD_OP_ZERO && - opcode != CEPH_OSD_OP_TRUNCATE); + opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE); op->extent.offset = offset; op->extent.length = length; @@ -663,7 +662,6 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req, case CEPH_OSD_OP_READ: case CEPH_OSD_OP_WRITE: case CEPH_OSD_OP_ZERO: - case CEPH_OSD_OP_DELETE: case CEPH_OSD_OP_TRUNCATE: if (src->op == CEPH_OSD_OP_WRITE) request_data_len = src->extent.length; @@ -723,6 +721,9 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req, ceph_osdc_msg_data_add(req->r_request, osd_data); request_data_len = osd_data->pagelist->length; break; + case CEPH_OSD_OP_CREATE: + case CEPH_OSD_OP_DELETE: + break; default: pr_err("unsupported osd opcode %s\n", ceph_osd_op_name(src->op)); @@ -763,13 +764,11 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, u64 objnum = 0; u64 objoff = 0; u64 objlen = 0; - u32 object_size; - u64 object_base; int r; BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE && - opcode != CEPH_OSD_OP_DELETE && opcode != CEPH_OSD_OP_ZERO && - opcode != CEPH_OSD_OP_TRUNCATE); + opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE && + opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE); req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool, GFP_NOFS); @@ -785,21 +784,24 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, return ERR_PTR(r); } - object_size = le32_to_cpu(layout->fl_object_size); - object_base = off - objoff; - if (!(truncate_seq == 1 && truncate_size == -1ULL)) { - if (truncate_size <= object_base) { - truncate_size = 0; - } else { - truncate_size -= object_base; - if (truncate_size > object_size) - truncate_size = object_size; + if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) { + osd_req_op_init(req, 0, opcode); + } else { + u32 object_size = le32_to_cpu(layout->fl_object_size); + u32 object_base = off - objoff; + if (!(truncate_seq == 1 && truncate_size == -1ULL)) { + if (truncate_size <= object_base) { + truncate_size = 0; + } else { + truncate_size -= object_base; + if (truncate_size > object_size) + truncate_size = object_size; + } } - } - - osd_req_op_extent_init(req, 0, opcode, objoff, objlen, - truncate_size, truncate_seq); + osd_req_op_extent_init(req, 0, opcode, objoff, objlen, + truncate_size, truncate_seq); + } /* * A second op in the ops array means the caller wants to * also issue a include a 'startsync' command so that the -- cgit v1.2.3 From 715e4cd405cfd67bd058e410b3e599bab2072645 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Thu, 13 Nov 2014 14:40:37 +0800 Subject: libceph: specify position of extent operation allow specifying position of extent operation in multi-operations osd request. This is required for cephfs to convert inline data to normal data (compare xattr, then write object). Signed-off-by: Yan, Zheng Reviewed-by: Ilya Dryomov --- fs/ceph/addr.c | 9 ++++++--- fs/ceph/file.c | 8 +++++--- include/linux/ceph/osd_client.h | 3 ++- net/ceph/osd_client.c | 19 ++++++------------- 4 files changed, 19 insertions(+), 20 deletions(-) (limited to 'net') diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 18c06bbaf136..f2c7aa878aa4 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -319,7 +319,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) off, len); vino = ceph_vino(inode); req = ceph_osdc_new_request(osdc, &ci->i_layout, vino, off, &len, - 1, CEPH_OSD_OP_READ, + 0, 1, CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ, NULL, ci->i_truncate_seq, ci->i_truncate_size, false); @@ -750,7 +750,6 @@ retry: last_snapc = snapc; while (!done && index <= end) { - int num_ops = do_sync ? 2 : 1; unsigned i; int first; pgoff_t next; @@ -850,7 +849,8 @@ get_more_pages: len = wsize; req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, - offset, &len, num_ops, + offset, &len, 0, + do_sync ? 2 : 1, CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK, @@ -862,6 +862,9 @@ get_more_pages: break; } + if (do_sync) + osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC); + req->r_callback = writepages_finish; req->r_inode = inode; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d7e0da8366e6..c03ac4c4bcd1 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -598,7 +598,7 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) snapc = ci->i_snap_realm->cached_context; vino = ceph_vino(inode); req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, - vino, pos, &len, + vino, pos, &len, 0, 2,/*include a 'startsync' command*/ CEPH_OSD_OP_WRITE, flags, snapc, ci->i_truncate_seq, @@ -609,6 +609,8 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) break; } + osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC); + n = iov_iter_get_pages_alloc(from, &pages, len, &start); if (unlikely(n < 0)) { ret = n; @@ -713,7 +715,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) snapc = ci->i_snap_realm->cached_context; vino = ceph_vino(inode); req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, - vino, pos, &len, 1, + vino, pos, &len, 0, 1, CEPH_OSD_OP_WRITE, flags, snapc, ci->i_truncate_seq, ci->i_truncate_size, @@ -1111,7 +1113,7 @@ static int ceph_zero_partial_object(struct inode *inode, req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, ceph_vino(inode), offset, length, - 1, op, + 0, 1, op, CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK, NULL, 0, 0, false); diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index bcf9c2180ea5..5d86416d35f2 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -328,7 +328,8 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, struct ceph_file_layout *layout, struct ceph_vino vino, u64 offset, u64 *len, - int num_ops, int opcode, int flags, + unsigned int which, int num_ops, + int opcode, int flags, struct ceph_snap_context *snapc, u32 truncate_seq, u64 truncate_size, bool use_mempool); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index af1b3ee195e9..53299c7b0ca4 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -753,7 +753,8 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req, struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, struct ceph_file_layout *layout, struct ceph_vino vino, - u64 off, u64 *plen, int num_ops, + u64 off, u64 *plen, + unsigned int which, int num_ops, int opcode, int flags, struct ceph_snap_context *snapc, u32 truncate_seq, @@ -785,7 +786,7 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, } if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) { - osd_req_op_init(req, 0, opcode); + osd_req_op_init(req, which, opcode); } else { u32 object_size = le32_to_cpu(layout->fl_object_size); u32 object_base = off - objoff; @@ -798,17 +799,9 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, truncate_size = object_size; } } - - osd_req_op_extent_init(req, 0, opcode, objoff, objlen, + osd_req_op_extent_init(req, which, opcode, objoff, objlen, truncate_size, truncate_seq); } - /* - * A second op in the ops array means the caller wants to - * also issue a include a 'startsync' command so that the - * osd will flush data quickly. - */ - if (num_ops > 1) - osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC); req->r_base_oloc.pool = ceph_file_layout_pg_pool(*layout); @@ -2675,7 +2668,7 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc, dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino, vino.snap, off, *plen); - req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 1, + req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 0, 1, CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ, NULL, truncate_seq, truncate_size, false); @@ -2718,7 +2711,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino, int page_align = off & ~PAGE_MASK; BUG_ON(vino.snap != CEPH_NOSNAP); /* snapshots aren't writeable */ - req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 1, + req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 0, 1, CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE, snapc, truncate_seq, truncate_size, -- cgit v1.2.3